Loading page content
GLM-5Open
Tool use · Reasoning
Evaluation overview
Overall rank
#45
76.4 points · 180 models
Open-weight rank
#11
85.6 points · 109 models
Data coverage
45 items
5 sources · updated through 2026-07-16
Domain performance
Coding#37 / 160
78.3
Research#42 / 174
87.4
Agents#45 / 125
73.3
Long context#48 / 82
72.6
Evaluation highlights
All evaluationsBasic information
- Context (input / output)
- 205K / 131K
- Parameters
- 744B / 40B active
- Release date
- 2026-02
- License
- MIT
- Input modalities
- Text
- Output modalities
- Text
- Architecture
- MoE (256 experts), DSA
- Active parameters
- 40B
Availability
Zhipu AIFull pricing
- Input
- ≈ $0.5714 /1M
- Output
- ≈ $2.5714 /1M
vLLM · FP8Deployment options
FP8 · 8 × 141 GB VRAM
Related links
Version relationships
GLM-5 family